Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 71 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.9035. Min Act: -0.0000

Data Index: 849736 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.5909. Min Act: -0.0000

Data Index: 117904 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.4002. Min Act: -0.0000

Data Index: 708850 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.3733. Min Act: -0.0000

Data Index: 810022 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.4539. Min Act: -0.0000

Data Index: 1161078 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.2484. Min Act: -0.0000

Data Index: 510384 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.2182. Min Act: -0.0000

Data Index: 771189 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.2051. Min Act: -0.0000

Data Index: 153808 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.1875. Min Act: -0.0000

Data Index: 501743 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.1130. Min Act: -0.0000

Data Index: 11174 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.7775. Min Act: -0.0000

Data Index: 288505 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.9262. Min Act: -0.0000

Data Index: 198924 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.8723. Min Act: -0.0000

Data Index: 385509 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.9035. Min Range: -3.9035

Max Act: 3.2163. Min Act: -0.0000

Data Index: 529998 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.9422. Min Act: -0.0000

Data Index: 763953 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.9146. Min Act: -0.0000

Data Index: 960370 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.7649. Min Act: -0.0000

Data Index: 1336192 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.9850. Min Act: -0.0000

Data Index: 826591 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.6870. Min Act: -0.0000

Data Index: 750158 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 3.9035. Min Range: -3.9035

Max Act: 2.9620. Min Act: -0.0000

Data Index: 49708 (C4 (Web Text))

Max Activating Token Index: 918